Prediction and simulation of battery pack usage for intelligent service robot deployment at a train station Löwen, Alexander Aleman-Gallegos, Enrique Aimiyekagbon, Osarenren Wachsmuth, Sven Sextro, Walter <jats:p>In order to make rail transportation more attractive compared to motorized private transport, intelligent solutions are required across the entire mobility chain. Train stations, as places of connection and transfer, offer the greatest potential in this context. Thus, the deployment of autonomous service robots at train stations offers a wide range of possibilities for supporting passengers on their journeys by rail, for example, by providing information, accompanying them to the next link in the mobility chain, or transporting their luggage. Since such robots are battery-powered, one challenge is to carefully plan activities based on the remaining battery capacity. Therefore, the aim of this work is to predict battery usage and, in turn, battery state, in order to inform passengers, and to enable intelligent planning of its usage.In this work, realistic operational conditions of a service robot are systematically assessed through measurements on the service robot itself and through passenger surveys at a train station. The estimated operational conditions are experimentally replicated to simulate the heterogeneous use of the battery pack, while acquiring condition monitoring data throughout its use. The battery pack is modeled based on the single particle model, which can robustly predict the battery state by simulating its usage considering past operational conditions. The approach is validated using experimental data obtained from simulating realistic usage. On the one hand, additional battery packs are employed, and on the other hand, the load is varied. The advantage of this approach lies in the ability to account for future changes, such as higher loads than anticipated, to provide robust predictions.This enables the intelligent use of service robots, offering passengers an improved service experience at train stations.</jats:p> PHM Society 2026 info:eu-repo/semantics/conferenceObject doc-type:conferenceObject text http://purl.org/coar/resource_type/c_5794 https://ris.uni-paderborn.de/record/67019 Löwen A, Aleman-Gallegos E, Aimiyekagbon O, Wachsmuth S, Sextro W. Prediction and simulation of battery pack usage for intelligent service robot deployment at a train station. In: <i>PHM Society European Conference</i>. Vol 9. PHM Society; 2026:1-10. doi:<a href="https://doi.org/10.36001/phme.2026.v9i1.4952">10.36001/phme.2026.v9i1.4952</a> eng info:eu-repo/semantics/altIdentifier/doi/10.36001/phme.2026.v9i1.4952 info:eu-repo/semantics/altIdentifier/issn/2325-016X info:eu-repo/semantics/altIdentifier/issn/2325-016X info:eu-repo/semantics/openAccess